Created
February 21, 2018 22:06
-
-
Save mattspence/a54a8733e5d75675b4abf527471a7614 to your computer and use it in GitHub Desktop.
Count First, Second, and Third+ Generations from 2015, 2016, and 2017 CPS Public Use Microdata
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(tidyverse) | |
download.file("http://thedataweb.rm.census.gov/pub/cps/march/asec2017_pubuse.zip", "asec2017_pubuse.zip") | |
download.file("http://thedataweb.rm.census.gov/pub/cps/march/asec2016_pubuse_v3.zip", "asec2016_pubuse.zip") | |
download.file("http://thedataweb.rm.census.gov/pub/cps/march/asec2015_pubuse.zip", "asec2015_pubuse.zip") | |
unzip("asec2017_pubuse.zip", "asec2017_pubuse.dat") | |
unzip("asec2016_pubuse.zip", "asec2016_pubuse_v3.dat") | |
unzip("asec2015_pubuse.zip", "asec2015_pubuse.dat") | |
gendata <- function(flnm){ | |
read_fwf(flnm, | |
fwf_cols(rectype=c(1,1), | |
hhseq=c(2,6), | |
sex=c(24,24), | |
hisp=c(31,31), | |
pob=c(84,86), | |
mpob=c(87,89), | |
fpob=c(90,92), | |
nativity=c(95,95), | |
basicwgt=c(139,146), | |
marchwgt=c(155,162) | |
), col_types = "cccccccccc") %>% | |
filter(rectype=="3") %>% | |
mutate(basicwgt = as.numeric(basicwgt)/100, marchwgt=as.numeric(marchwgt)/100) %>% | |
mutate(pob = as.numeric(pob), fpob=as.numeric(fpob),mpob=as.numeric(mpob)) %>% | |
mutate(generation = case_when( | |
nativity %in% c('4','5') ~ '1', | |
nativity %in% c('1','2','3') & mpob < 100 & fpob >=100 ~ '2', | |
nativity %in% c('1','2','3') & mpob >= 100 & fpob < 100 ~ '2', | |
nativity %in% c('1','2','3') & mpob >= 100 & fpob >= 100 ~ '2', | |
nativity %in% c('1','2','3') & mpob < 100 & fpob < 100 ~ '3', | |
TRUE ~ '99')) | |
} | |
pers15 <- gendata("asec2015_pubuse.dat") | |
pers16 <- gendata("asec2016_pubuse_v3.dat") | |
pers17 <- gendata("asec2017_pubuse.dat") | |
pers15 %>% group_by(generation) %>% summarize(n=sum(marchwgt)/1000) | |
pers16 %>% group_by(generation) %>% summarize(n=sum(marchwgt)/1000) | |
pers17 %>% group_by(generation) %>% summarize(n=sum(marchwgt)/1000) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment